Threat-detection firm Perception Point has launched a tool for preventing AI-generated email threats.
The new tool leverages large language models and deep-learning architecture to detect generative AI-fueled Business Email Compromise (BEC) attacks.
The goal is to “prevent these threats before they even reach the user’s inbox,” says Tal Zamir, CTO of Perception Point.
The Tel Aviv-based firm utilizes a three-phase architecture to minimize false positives.
Initial scoring is followed by categorizing of the email content using transformers and clustering algorithms, combining those insights data such as sender reputation and authentication protocol information.
"Amid an increasingly complex threat landscape, there is an urgent need for cutting-edge defenses against Gen AI-powered threats," Zamir says. “We're being challenged as an industry with yet another avenue that bad actors have come to exploit in their ever-expanding range of attacks."